理論部分
- 相關概念
- 生成模型
- 判別模型
- 樸素貝葉斯基本原理
- 條件概率公式
- 乘法公式
- 全概率公式
- 貝葉斯定理
- 特徵條件獨立假設
- 後驗概率最大化
- 拉普拉斯平滑
- 樸素貝葉斯的三種形式
- 高斯型
- 多項式型
- 伯努利型
- 極值問題情況下的每個類的分類概率
- 下溢問題如何解決
- 零概率問題如何解決
- sklearn參數詳解
實戰部分
- 利用
sklearn
解決聚類問題。 sklearn.naive_bayes.GaussianNB
import math
class NaiveBayes:
def __init__(self):
self.model = None
# 數學期望
@staticmethod
def mean(X):
"""計算均值
Param: X : list or np.ndarray
Return:
avg : float
"""
avg = 0.0
# ========= show me your code ==================
avg = np.mean(X)
# ========= show me your code ==================
return avg
def stdev(self, X):
"""計算標準差
Param: X : list or np.ndarray
Return:
res : float
"""
res = 0.0
res = math.sqrt(np.mean(np.square(X-self.mean(X))))
return res
def gaussian_probability(self, x, mean, stdev):
"""
根據均值和標註差計算x符號該高斯分佈的概率
Parameters:
----------
x : 輸入
mean : 均值
stdev : 標準差
Return:
res : float, x符合的概率值
"""
res = 0.0
exp = math.exp(-math.pow(x - mean, 2) / 2 * math.pow(stdev, 2))
res = (1 / (math.sqrt(2 * math.pi) * stdev)) * exp
return res
def summarize(self, train_data):
"""計算每個類目下對應數據的均值和標準差
Param: train_data : list
Return : [mean, stdev]
"""
summaries = [0.0, 0.0]
summaries = [(self.mean(i), self.stdev(i)) for i in zip(*train_data)]
return summaries
def fit(self, X, y):
labels = list(set(y))
data = {label: [] for label in labels}
for f, label in zip(X, y):
data[label].append(f)
self.model = {
label: self.summarize(value) for label, value in data.items()
}
return 'gaussianNB train done!'
# 計算概率
def calculate_probabilities(self, input_data):
"""計算數據在各個高斯分佈下的概率
Paramter:
input_data : 輸入數據
Return:
probabilities : {label : p}
"""
# summaries:{0.0: [(5.0, 0.37),(3.42, 0.40)], 1.0: [(5.8, 0.449),(2.7, 0.27)]}
# input_data:[1.1, 2.2]
probabilities = {}
# ========= show me your code ==================
for label, value in self.model.items():
probabilities[label] = 1
for i in range(len(value)):
mean, stdev = value[i]
probabilities[label] *= self.gaussian_probability(input_data[i], mean, stdev)
return probabilities
def predict(self, X_test):
# {0.0: 2.9680340789325763e-27, 1.0: 3.5749783019849535e-26}
label = sorted(self.calculate_probabilities(X_test).items(), key=lambda x: x[-1])[-1][0]
return label
# 計算得分
def score(self, X_test, y_test):
right = 0
for X, y in zip(X_test, y_test):
label = self.predict(X)
if label == y:
right += 1
return right / float(len(X_test))